A new automatic sleep staging system based on statistical behavior of local extrema using single channel EEG signal
Introduction
Sleep is a reversible state of mind and body, characterized by increased level of unconsciousness and perceptual disengagement from the surrounding world. It is distinguished from wakefulness by a decreased ability to respond to environmental stimuli (Allada & Siegel, 2008). Since human beings spend approximately one-third of their lifetimes sleeping, it is essential to overall health and well-being so that the lack of sleep can directly influence our mood and cognitive performances (Touchette et al., 2007, Walker and Stickgold, 2006).
A widely adopted technique in sleep studies, specifically in the diagnosis of sleep disorders, is Polysomnography (PSG). PSG is a multi-parametric test that monitors many body functions by recording electrophysiological signals such as Electroencephalogram (EEG), Electrooculogram (EOG), Electromyogram (EMG) and Electrocardiogram (ECG) signals (Álvarez-Estévez & Moret-Bonillo, 2011). Two well-known gold standards for interpreting sleep recordings are Rechtschaffen and Kales (R&K) criteria and the guideline developed by the American Academy of Sleep Medicine (AASM). According to R&K recommendations, each 20 or 30 s epoch of an overnight sleep belongs to one of the seven discrete stages: Wake (wakefulness), S1 (drowsiness), S2 (light sleep), S3 (deep sleep), S4 (deep or slow wave sleep), REM (rapid eye movement), and movement time (MT) (Rechtschaffen & Kales, 1968). AASM modified R&K criteria and developed a new guideline for scoring of sleep-related phenomena (Iber, 2007). The major distinction between AASM and R&K guidelines are: (1) NREM stages (S1, S2, S3, and S4) in R&K are referred to as stages N1, N2, and N3 in the AASM. In this case, N3 (deep or delta-wave sleep) is obtained by merging stages S3 and S4; (2) Stages Wake and REM in R&K are renamed to as stages W and R, respectively; (3) Stage movement time (MT) is abolished in AASM guideline; (4) EEG derivations of R&K criteria, i.e. C3-A2, and O2-A1, are replaced with F4-M1, C4-M1, and O2-M1 derivations by AASM (Iber, 2007, Moser et al., 2009, Rechtschaffen and Kales, 1968). Furthermore, according to AASM criteria, the scoring of PSG recordings enhances the amount of light and deep sleep in comparison to R&K criteria (Moser et al., 2009).
The process of visually scoring of sleep stages is complex, time-consuming, and prone to human errors. Due to inter- and intra-scorer variability, the level of agreement in visual sleep stage scoring differs greatly among scorers, even by recording or by diagnosis (Collop, 2002, Norman et al., 2000). For these reasons, designing an accurate and robust automatic sleep stage scoring system can significantly reduce the scoring time and generate reliable results. The first attempts to devise such systems have been begun more than four decades ago (Fraiwan et al., 2010). Nowadays, by developing innovative signal processing techniques and heuristic machine learning methods, a large number of methods have been proposed to automatically classify sleep stages.
Since EEG patterns exhibit different characteristics during the sleep stages (Fig. 1), numerous automatic systems for sleep stage classification have constructed based on EEG signals (Doroshenkov et al., 2007, Flexer et al., 2005, Shi et al., 2015). In addition, more complex approaches have utilized EOG and EMG signals in combination with EEG for extracting relevant features (Liang, Kuo, Hu, Pan, & Wang, 2012a; Liang et al., 2016; Liang, Kuo, Hu, & Cheng, 2012b; Tagluk, Sezgin, & Akin, 2010). Some studies have also focused on other physiologic signals such as ECG and respiratory signals to design an automatic sleep stage scoring system (Ebrahimi et al., 2015, Ebrahimi et al., 2013, Virkkala et al., 2007).
Generally, EEG signal processing techniques applied to human sleep staging perform in three main steps: pre-processing, feature extraction, and classification. Two most popular approaches in pre-processing step are artifact removal (to eliminate or reduce the effects of artifacts on EEG signals) and segmentation (to overcome the non-stationary nature of EEG signals) (Motamedi-Fakhr, Moshrefi-Torbati, Hill, Hill, & White, 2014).
Various methods have been developed to extract proper information from sleep EEG signals. All of these techniques can classify into four main categories: temporal features, spectral features, time-frequency features, and nonlinear features (Aboalayon et al., 2016, Motamedi-Fakhr et al., 2014). Some of the ubiquitous temporal features, which represent characteristics of a signal in the time domain space, are mean, mode, median, variance, standard deviation, skewness, kurtosis, zero-crossing, and Hjorth parameters (Diykh & Li, 2016; Diykh, Li, & Wen, 2016; Şen, Peker, Çavuşoğlu, & Çelebi, 2014). To obtain spectral features or frequency-based features, the time domain signals are converted into the frequency domain using the Fourier transforms. The more prevalent spectral features in sleep EEG signal processing are parametric and nonparametric power spectral density (PSD) and higher-order spectral analysis (HOS) (Acharya et al., 2015, Acharya et al., 2010, Radha et al., 2014). Time-frequency features such as short time Fourier transform (STFT), wavelet transform (WT), and empirical mode decomposition (EMD) decompose a signal into both of time domain and frequency domain (Hassan and Haque, 2016a, Hassan and Hassan Bhuiyan, 2016, Sanders et al., 2014, Şen et al., 2014). Nonlinear and entropy-based features such as fractal dimension (FD), correlation dimension (CD), entropy measures, and Lyapunov exponent can also provide complementary information about main characteristics of different sleep stages (Peker, 2016, Şen et al., 2014).
So far, a wide variety of various classification techniques have been utilized in sleep staging studies, but the ubiquitous classifiers are Artificial Neural Networks (ANN) (Ronzhina et al., 2012), k-means (Agarwal & Gotman, 2001), Self-Organizing Maps (SOM) (Ouanes & Rejeb, 2016), Linear Discriminant Analysis (LDA) (Fraiwan et al., 2010), Support Vector Machines (SVM) (Enshaeifar, Kouchaki, Took, & Sanei, 2016), Hidden Markov Model (HMM) (Doroshenkov et al., 2007), and ensemble classifiers such as Adaptive Boosting (Adaboost) (Hassan, 2016), Linear Programming Boosting (LPBoost) (Hassan & Subasi, 2016), Bootstrap Aggregating (Bagging) (Hassan and Haque, 2016b, Hassan et al., 2016), and Random Under Sampling Boosting (RUSBost) (Hassan and Haque, 2016a, Hassan and Haque, 2017).
Recently, it has been observed an increasing trend of interest in time series data analysis by employing symbolic approach. Symbolic analysis of time series can increase the efficiency of findings, reduce sensitivity to measurement noise, and discriminate both specific and general classes of proposed models. Symbolic techniques provide a general description of a dynamical system by transforming a system into a new representation space (so that most of the significant temporal information is retained), assigning a set of symbols (which each symbol corresponds to a given state of a system), and extracting invaluable information from the new space (Amigo et al., 2014, Daw et al., 2003, Lin et al., 2003). As a mathematical tool, it presents a useful measure to assess the complexity or the irregularity of biomedical recordings (Balakrishnan et al., 2010, Canelas et al., 2012). One of the basic methods in the symbolic analysis of time series, which reduces the dimensionality of signals by discretizing, is the Symbolic Aggregate approximation (SAX). The distance in the SAX has a lower bound to the Euclidean distance (Lin, Keogh, Wei, & Lonardi, 2007). In recent years, some extensions have been presented to enhance the capability and efficacy of the SAX method. The extended symbolic aggregate approximation (ESAX) could overcome some of the limitations of SAX. In this method, the SAX dimensions were tripled by incorporating the minimum and maximum information of time series (Lkhagva, Suzuki, & Kawagoe, 2006). The ESAX Statistical Vector Space (ESSVS) reduced the complexity of the cluster computing process of the SAX by replacing Euclidean distance to Cosine distance (Jiang, Lan, & Zhang, 2009). The trend distance SAX (SAX-TD) designed a measure to compute the distance of trends using the starting and the ending points of segments by proposing a modified distance measure that integrated the SAX distance with a weighted trend distance (Sun, Li, Liu, Sun, & Chow, 2014). The adaptive SAX (aSAX) presented a novel adaptive symbolic approach based on the combination of SAX and k-means algorithm to boost performances of the classic SAX (Pham, Le, & Dang, 2010). The indexable SAX (iSAX) is a superset of classic SAX and show how it can modify SAX to be a multiresolution representation, similar in spirit to wavelets. This approach also allows for both fast exact search and ultra-fast approximate search (Shieh & Keogh, 2008).
The SAX and all its extensions only describe a specific signal in the time domain. However, in nonlinear and chaotic signals (like EEG), dynamics of a system plays a prominent role. In this study, a novel temporal feature named statistical behavior of local extreme (SBLE) is propounded based on dynamical characteristics of EEG signals. In other words, SBLE is a symbolic technique to compare and track the dynamics of sleep EEG signals through various sleep stages. The principal advantage of SBLE is its potency to detect the hidden dynamical and behavioral changes of sleep EEG signals in the process of transforming a given stage into other stages. These alterations are specifically traceable in different frequency bands.
In general, physicians and sleep experts score the sleep stages according to the morphological characteristics of EEG signals. Thus, these morphological alternations have unique information, which by quantifying and symbolizing of it, an efficient feature set can be proposed to construct a precise sleep stage scoring system. In fact, the main hypothesis and contribution of this study is to propose a novel time-domain feature, which can automatically detect various sleep stages based on morphological changes of sleep EEG signals, similar to the point of view of sleep experts.
Originally, the main idea of the novel time domain feature (SBLE) propound herein was introduced in our previous works and its effectiveness was evaluated to predict epileptic seizures and detect the activation phase (A phase) of sleep Cyclic Alternating Pattern (CAP) (Niknazar and Nasrabadi, 2016, Niknazar et al., 2015a, Niknazar et al., 2015b). In the aforementioned studies, SBLE was mainly utilized as a similarity index to address our hypotheses. In the present study, to maximize the generalization ability of SBLE, a series of modifications and extensions were conducted. As a result, these improvements promoted the performance of SBLE as an effective time domain feature to handle the multi-class classification of sleep stages compared to the previous one. These changes will be discussed in detail in Section 3.
Section snippets
Related works
Hassan and Bhuiyan, 2016b, Hassan and Bhuiyan, 2017b) and Hassan and Hassan Bhuiyan (2016) decomposed EEG signals and extracted statistical moment-based features and adaptive noise features by using Empirical Mode Decomposition (EMD) technique. Then, by means of AdaBoost, Bagging, and RUSBoost classifiers, they reported 88.6%, 86.9%, and 88.1% as average accuracy for six-stage classification, respectively. Hassan and Bhuiyan, 2016a, Hassan and Bhuiyan, 2017a) and Hassan and Subasi (2017) also
Materials and methods
The scheme of the proposed automatic sleep stage scoring system is depicted in Fig. 2. In the first step, the entire epochs of dataset were randomly divided into two halves: the training set and the test set. Next, in the preprocessing block, the selected EEG channel was filtered and decomposed to the given frequency bands. Then, SBLE features were independently extracted from each frequency sub-bands. The discriminative features were selected by employing an appropriate feature selection
Experimental results
To evaluate the potency of the proposed framework, a set of comprehensive experiments were carefully designed and conducted. In different component of this section (i.e. the effect of different feature selection techniques on the classification results, statistical analysis of the selected features, the rationale of channel selection, feature evaluation, the classification results of different multi-class problems using Sleep-EDF dataset, the classification results for DREAMS Subject database,
Discussion
The aim of the present study was to propose a robust and reliable computer-aided sleep stage scoring system to overcome the common difficulties of manual sleep staging. The rationale of each step of algorithmic development was discussed in detail, and the generalization of the proposed methodology was analyzed on a large number of sleep EEG epochs (more than 35,000 epochs) of Sleep-EDF dataset and DREAMS Subject Database. The main advantages and contribution of this paper can be summarized as
Conclusion
The main idea of this paper was to implement an expert system for multi-class classification of sleep stages based on tracking the dynamical changes of EEG signals. For this purpose, a novel time domain feature named SBLE was proposed. In this method, amplitude values of local extrema are quantized into some intervals to quantify the dynamical behavior of signals by considering a series of micro and macro patterns. Comparing with other existing studies, the automatic sleep staging approach
References (109)
- et al.
Unearthing the phylogenetic roots of sleep
Current Biology
(2008) - et al.
Automatic classification of sleep stages based on the time-frequency image of EEG signals
Computer Methods and Programs in Biomedicine
(2013) - et al.
Self-evaluated automatic classifier as a decision-support tool for sleep/wake staging
Computers in Biology and Medicine
(2011) Scoring variability between polysomnography technologists in different sleep laboratories
Sleep Medicine
(2002)- et al.
Complex networks approach for EEG signal sleep stages classification
Expert Systems with Applications
(2016) - et al.
Automatic sleep staging using empirical mode decomposition, discrete wavelet transform, time-domain, and nonlinear dynamics features of heart rate variability signals
Computer Methods and Programs in Biomedicine
(2013) - et al.
Automatic sleep staging by simultaneous analysis of ECG and respiratory signals in long epochs
Biomedical Signal Processing and Control
(2015) - et al.
A reliable probabilistic sleep stager based on a single EEG signal
Artificial Intelligence in Medicine
(2005) - et al.
Efficient sleep stage recognition system based on EEG signal using k-means clustering based feature weighting
Expert Systems with Applications
(2010) Computer-aided obstructive sleep apnea detection using normal inverse Gaussian parameters and adaptive boosting
Biomedical Signal Processing and Control
(2016)
A decision support system for automatic sleep staging from EEG signals using tunable Q-factor wavelet transform and spectral features
Journal of Neuroscience Methods
Computer-aided sleep staging using complete ensemble empirical mode decomposition with adaptive noise and bootstrap aggregating
Biomedical Signal Processing and Control
An automated method for sleep staging from EEG signals using normal inverse Gaussian parameters and adaptive boosting
Neurocomputing
Automated identification of sleep states from EEG signals by means of ensemble empirical mode decomposition and random under sampling boosting
Computer Methods and Programs in Biomedicine
Computer-aided obstructive sleep apnea screening from single-lead electrocardiogram using statistical and spectral features and bootstrap aggregating
Biocybernetics and Biomedical Engineering
An expert system for automated identification of obstructive sleep apnea from single-lead ECG using random under sampling boosting
Neurocomputing
Automatic sleep scoring using statistical features in the EMD domain and ensemble methods
Biocybernetics and Biomedical Engineering
Epileptic seizure detection in EEG signals using tunable-Q factor wavelet transform and bootstrap aggregating
Computer Methods and Programs in Biomedicine
Automatic identification of epileptic seizures from EEG signals using linear programming boosting
Computer Methods and Programs in Biomedicine
A decision support system for automated identification of sleep stages from single-channel EEG signals
Knowledge-Based Systems
Why REM sleep? Clues beyond the laboratory in a more challenging world
Biological Psychology
Automatic sleep stage recurrent neural classifier using energy features of EEG signals
Neurocomputing
New methods of nonlinear and symbolic dynamics in sleep EEG-signal analysis
IFAC Proceedings
Automatic sleep scoring: A search for an optimal combination of measures
Artificial Intelligence in Medicine
Learning machines and sleeping brains: Automatic sleep stage classification using decision-tree multi-class support vector machines
Journal of Neuroscience Methods
The measurement of observer agreement for categorical data
Biometrics
Combination of expert knowledge and a genetic fuzzy inference system for automatic sleep staging
IEEE Transactions on Bio-Medical Engineering
Experiencing SAX: A novel symbolic representation of time series
Data Mining and Knowledge Discovery
Epileptic seizure prediction using statistical behavior of local extrema and fuzzy logic system
International Journal of Computer Applications
Large Margin DAG's for Multiclass Classification
Microsoft Research
iSAX: indexing and mining terabyte sized time series
Estimation of sleep stages by an artificial neural network employing EEG, EMG and EOG
Journal of Medical Systems
Sleep stage classification using EEG signal analysis: A comprehensive survey and new investigation
Entropy
Nonlinear dynamics measures for automated EEG-based sleep stage detection
European Neurology
Analysis and automatic identification of sleep stages using higher order spectra
International Journal of Neural Systems
Computer-assisted sleep staging
IEEE Transactions on Biomedical Engineering
Identific of electroencephalographic arousals in multichannel sleep recordings
IEEE Transactions on Biomedical Engineering
Ordinal symbolic analysis and its application to biomedical recordings
Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
Creating symbolic representations of electroencephalographic signals: an investigation of alternate methodologies on intracranial data
Comparison between five classifiers for automatic scoring of human sleep recordings
Automatic analysis of single-channel sleep EEG: Validation in healthy individuals
Sleep
Pattern Recognition and Machine Learning (Information Science and Statistics)
Unsupervised feature selection for multi-cluster data
A new SAX-GA methodology applied to investment strategies optimization
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology
Sleep electroencephalogram analysis based on symbolic transfer entropy
Advanced Materials Research
A Coefficient of Agreement for Nominal Scales
Educational and Psychological Measurement
A review of symbolic analysis of experimental data
Review of Scientific Instruments
Solving Multiclass Learning Problems via Error-correcting Output Codes
Journal of Artificial Intelligence Research
Cited by (77)
A federated semi-supervised automatic sleep staging method based on relationship knowledge sharing
2024, Expert Systems with ApplicationsCTCNet: A CNN Transformer capsule network for sleep stage classification
2024, Measurement: Journal of the International Measurement ConfederationMultivariate phase space reconstruction and Riemannian manifold for sleep stage classification
2024, Biomedical Signal Processing and ControlA review of automated sleep stage scoring
2023, Encyclopedia of Sleep and Circadian Rhythms: Volume 1-6, Second EditionA dual-stream deep neural network integrated with adaptive boosting for sleep staging
2023, Biomedical Signal Processing and Control